DeepMind-Princeton paper shows LLMs causally use confidence to decide whether to answer

GoogleDeepMind · x · 2026-09-07

Researchers from Google DeepMind and Princeton (lead author Dharshan Kumaran) published an open-access Nature Machine Intelligence paper offering causal evidence that LLMs use confidence signals to drive behavior, not just passively report them.

Key points:

Conclusion: models genuinely use their own confidence to decide whether to answer or abstain, paralleling metacognition in biological systems.

Original post →

More from Models

Models channel →